© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152665
    Prev
    Next
    INDEX
    Explanations

    recommendation context

    np_acts-logits-general · gemini-2.5-flash-lite

    describing what indicates or follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    पोज
    0.56
    收益
    0.53
     ಪ್ರಯೋಜನ
    0.51
    ᡵ
    0.50
    헷
    0.50
     kalah
    0.48
    蝠
    0.48
    ੲ
    0.48
    醯
    0.47
    リエ
    0.47
    POSITIVE LOGITS
     |
    0.55
    human
    0.45
     |-
    0.45
     Recommendations
    0.44
    produktion
    0.44
    individual
    0.44
     starten
    0.44
    occurrence
    0.44
    umbr
    0.43
    iv
    0.43
    Activations Density 0.000%

    No Known Activations